bioguider 0.2.8__py3-none-any.whl → 0.2.10__py3-none-any.whl

bioguider/agents/agent_tools.py

@@ -51,13 +51,22 @@ Returns:
         return content
 
 class summarize_file_tool(agent_tool):
-    """ read and summarize the file
-Args:
-    file_path str [required]: the file path
-    summarize_prompt str [required]: a prompt to guide how to summarize the file, if no prompt needed, please set "N/A"
-Returns:
-    A string of summarized file content, if the file does not exist, return None.         
-        """
+    """ Read a file and generate a summary according to a specified prompt.
+
+Arguments
+----------
+    file_path : str, required
+        Path to the file to read.
+    summarize_prompt : str, optional
+        Instruction guiding the summarization focus (default is "N/A").
+        Use this to emphasize specific aspects of the content.
+
+Returns
+-------
+    str or None
+        A summarized version of the file content.
+        Returns None if the file does not exist or cannot be read.     
+    """
     def __init__(
         self, 
         llm: BaseChatOpenAI,
@@ -96,7 +105,7 @@ Returns:
             summarized_text=summarized_text,
             token_usage=token_usage,
         )
-    def run(self, file_path: str, summarize_prompt: str) -> str | None:
+    def run(self, file_path: str, summarize_prompt: str = "N/A") -> str | None:
         if file_path is None:
             return None
         if summarize_prompt is None or len(summarize_prompt) == 0:

bioguider/agents/common_agent_2step.py

@@ -154,7 +154,7 @@ class CommonAgentTwoChainSteps(CommonAgentTwoSteps):
     def _invoke_agent(self, system_prompt, instruction_prompt, schema, post_process = None, **kwargs):
         # Initialize the callback handler
         callback_handler = OpenAICallbackHandler()
-        processed_system_prompt = system_prompt.replace("{", "(").replace("}", ")")
+        processed_system_prompt = system_prompt.replace("{", "{{").replace("}", "}}")
         cot_prompt = self._build_prompt_for_cot_step(
             system_prompt=processed_system_prompt, 
             instruction_prompt=instruction_prompt

bioguider/agents/evaluation_installation_task.py

@@ -52,14 +52,12 @@ Please assess the installation information using the following criteria. For eac
 
 Your response **must exactly follow** the structure below:
 
-```
 **FinalAnswer**
 **Overall Score:** [Poor / Fair / Good / Excellent]  
 **Ease of Access:** <your comments>  
 **Clarity of Dependency Specification:** <your comments>  
 **Hardware Requirements:** <your comments>  
 **Installation Guide:** <your comments>  
-```
 
 ---
 
@@ -149,6 +147,7 @@ class EvaluationInstallationTask(EvaluationTask):
             schema=EvaluationInstallationResultSchema,
         )
         res = EvaluationInstallationResult(**res)
+        self.print_step(step_output=reasoning_process)
         evaluation = {
             "score": res.score,
             "ease_of_access": res.ease_of_access,

bioguider/agents/evaluation_task.py

@@ -18,7 +18,8 @@ from ..utils.gitignore_checker import GitignoreChecker
 logger = logging.getLogger(__name__)
 
 EVALUATION_README_SYSTEM_PROMPT = """
-You are an expert in evaluating the quality of README files in software repositories. Your task is to analyze the provided README file and generate a comprehensive quality report.
+You are an expert in evaluating the quality of README files in software repositories. 
+Your task is to analyze the provided README file and generate a comprehensive quality report.
 
 ---
 
@@ -28,9 +29,10 @@ First, determine whether the provided README is a **project-level README** (typi
 
 ---
 
-### **Project-level README Evaluation**
+### **Evaluation Criteria**
+
+#### If the README is a **project-level** file, evaluate it using the following criteria.
 
-If the README is a **project-level** file, evaluate it using the following criteria.
 For each criterion below, provide a brief assessment followed by specific, actionable comments for improvement.
 
 **1. Project Clarity & Purpose**
@@ -38,30 +40,45 @@ For each criterion below, provide a brief assessment followed by specific, actio
  * **Improvement Suggestions**:
     * **Original text:** [Quote a specific line/section from the README.]
     * **Improving comments:** [Provide your suggestions to improve clarity.]
+    * **Original text:** [Quote a specific line/section from the README.]
+    * **Improving comments:** [Provide your suggestions to improve clarity.]
+    ...
 
 **2. Installation Instructions**
  * **Assessment**: [Your evaluation of the installation instructions.]
  * **Improvement Suggestions**:
     * **Original text:** [Quote text related to installation.]
     * **Improving comments:** [Provide your suggestions.]
+    * **Original text:** [Quote text related to installation.]
+    * **Improving comments:** [Provide your suggestions.]
+    ...
 
 **3. Usage Instructions**
  * **Assessment**: [Your evaluation of the usage instructions.]
  * **Improvement Suggestions**:
     * **Original text:** [Quote text related to usage.]
     * **Improving comments:** [Provide your suggestions.]
+    * **Original text:** [Quote text related to usage.]
+    * **Improving comments:** [Provide your suggestions.]
+    ...
 
 **4. Contributing Guidelines**
  * **Assessment**: [Your evaluation of the contributing guidelines.]
  * **Improvement Suggestions**:
     * **Original text:** [Quote text related to contributions.]
     * **Improving comments:** [Provide your suggestions.]
+    * **Original text:** [Quote text related to contributions.]
+    * **Improving comments:** [Provide your suggestions.]
+    ...
 
 **5. License Information**
  * **Assessment**: [Your evaluation of the license information.]
  * **Improvement Suggestions**:
     * **Original text:** [Quote text related to the license.]
     * **Improving comments:** [Provide your suggestions.]
+    * **Original text:** [Quote text related to the license.]
+    * **Improving comments:** [Provide your suggestions.]
+    ...
 
 **6. Readability Analysis**
  * **Flesch Reading Ease**: `{flesch_reading_ease}` (A higher score is better, with 60-70 being easily understood by most adults).
@@ -70,29 +87,9 @@ For each criterion below, provide a brief assessment followed by specific, actio
  * **SMOG Index**: `{smog_index}` (Estimates the years of education needed to understand the text).
  * **Assessment**: Based on these scores, evaluate the overall readability and technical complexity of the language used.
 
-**Final Answer**
- The final answer **must exactly match** the following format:
-```
-  * Project-Level README: Yes / No
-  * **Score:** <number from 0 to 100>  
-  * **Key Strengths**: <brief summary of the README's strongest points in 2-3 sentences> 
-  * **Overall Improvement Suggestions:**
-    - "Original text snippet 1" - Improving comment 1  
-    - "Original text snippet 2" - Improving comment 2  
-    - ...
-```
-
-  * **Project-Level README**: Indicate “Yes” if the README is project-level, otherwise “No.”
-  * **Score**: Provide an overall quality score (100 = perfect).
-  * **Key Strengths**: Provide the README's strongest points in 2-3 sentences
-  * **Overall Improvement Suggestions**:
-    * List each original text snippet that needs improvement, followed by your suggestion.
-
 ---
 
-### **Folder-Level README Evaluation**
-
-If the README is a **folder-level** file, use the following criteria instead.
+#### If if is a **folder-level** file, use the following criteria instead.
 
 For each criterion below, provide a brief assessment followed by specific, actionable comments for improvement.
 
@@ -121,15 +118,30 @@ For each criterion below, provide a brief assessment followed by specific, actio
  * **SMOG Index**: `{smog_index}` (Estimates the years of education needed to understand the text).
  * **Assessment**: Based on these scores, evaluate the overall readability and technical complexity of the language used.
 
-**Final Answer**
-  The final answer **must exactly match** the following format:
+---
+
+### Final Report Format
+
+#### Your output **must exactly match**  the following template:
+
+**FinalAnswer**
+
  * Project-Level README: Yes / No
- * **Score:** <number from 0 to 100>  
+ * **Score:** [Poor / Fair / Good / Excellent]
   * **Key Strengths**: <brief summary of the README's strongest points in 2-3 sentences> 
   * **Overall Improvement Suggestions:**
     - "Original text snippet 1" - Improving comment 1  
     - "Original text snippet 2" - Improving comment 2  
     - ...
+
+#### Notes
+
+* **Project-Level README**: "Yes" if root-level; "No" if folder-level.
+* **Score**: Overall quality rating, could be Poor / Fair / Good / Excellent.
+* **Key Strengths**: Briefly highlight the README's strongest aspects.
+* **Improvement Suggestions**: Provide concrete snippets and suggested improvements.
+
+
 ---
 
 ### **README path:**
@@ -188,7 +200,7 @@ class EvaluationTask(ABC):
 
 class EvaluationREADMEResult(BaseModel):
     project_level: Optional[bool]=Field(description="A boolean value specifying if the README file is **project-level** README. TRUE: project-level, FALSE, folder-level")
-    score: Optional[float]=Field(description="An overall score")
+    score: Optional[str]=Field(description="An overall score")
     key_strengths: Optional[str]=Field(description="A string specifying the key strengths of README file.")
     overall_improvement_suggestions: Optional[list[str]]=Field(description="A list of overall improvement suggestions")
 
@@ -202,7 +214,7 @@ EvaluationREADMEResultSchema = {
             "title": "Project Level"
         },
         "score": {
-            "anyOf": [{"type": "number"}, {"type": "null"}],
+            "anyOf": [{"type": "string"}, {"type": "null"}],
             "description": "An overall score",
             "title": "Score"
         },
@@ -248,7 +260,7 @@ class EvaluationREADMETask(EvaluationTask):
                 readme_evaluations[readme_file] = {
                     "evaluation": {
                         "project_level": "/" in readme_file,
-                        "score": 0,
+                        "score": "Poor",
                         "key_strengths": f"{readme_file} is an empty file.",
                         "overall_improvement_suggestions": f"{readme_file} is an empty file.",
                     },

bioguider/agents/identification_observe_step.py

@@ -25,7 +25,8 @@ Carefully review the **Goal**, **Repository File Structure**, and **Intermediate
   - Then provide your result under **FinalAnswer**  
   ```
   **Analysis**: your analysis here  
-  **FinalAnswer**: your final answer here, in json format **without** json fence (```json ... ```), like {final_answer_example}
+  **FinalAnswer**: your final answer here, in **raw json format**, **including** the surrounding "{{}}" but **without** using code fence (```json ... ```), 
+  For example, output exactly: {final_answer_example}
   ```
 - If the information is **not sufficient** to achieve the goal, simply explain why under **Thoughts**:  
   ```

bioguider/managers/evaluation_manager.py

@@ -25,8 +25,8 @@ class EvaluationManager:
         self.repo_url = repo_url
         self.rag = RAG()
         self.rag.initialize_db_manager()
-        self.rag.prepare_retriever(repo_url_or_path=repo_url)
-
+        self.rag.initialize_repo(repo_url_or_path=repo_url)
+        
         author, repo_name = parse_repo_url(repo_url)
         self.summary_file_db = SummarizedFilesDb(author, repo_name)
 

bioguider/rag/data_pipeline.py

@@ -504,7 +504,11 @@ class DatabaseManager:
         self.repo_url_or_path = None
         self.repo_paths = None
 
-    def prepare_database(self, repo_url_or_path: str, access_token: str = None) -> Tuple[List[Document], List[Document]]:
+    def reset_database_and_create_repo(self, repo_url_or_path: str, access_token: str = None):
+        self._reset_database()
+        self._create_repo(repo_url_or_path, access_token)
+
+    def prepare_database(self) -> Tuple[List[Document], List[Document]]:
         """
         Create a new database from the repository.
 
@@ -515,9 +519,7 @@ class DatabaseManager:
         Returns:
             Tuple[List[Document], List[Document]]: Tuple of two Lists of Document objects
         """
-        self.reset_database()
-        self._create_repo(repo_url_or_path, access_token)
-        return self.prepare_db_index()
+        return self._prepare_db_index()
     
     def _extract_repo_name_from_url(self, repo_url_or_path: str, repo_type: str) -> str:
         # Extract owner and repo name to create unique identifier
@@ -534,7 +536,7 @@ class DatabaseManager:
             repo_name = url_parts[-1].replace(".git", "")
         return repo_name
 
-    def reset_database(self):
+    def _reset_database(self):
         """
         Reset the database to its initial state.
         """
@@ -608,7 +610,7 @@ class DatabaseManager:
             return self.repo_paths["save_repo_dir"]
         return None
     
-    def prepare_db_index(self) -> Tuple[List[Document], List[Document]]:
+    def _prepare_db_index(self) -> Tuple[List[Document], List[Document]]:
         """
         Prepare the indexed database for the repository.
         :return: Tuple of two Lists of Document objects
@@ -647,16 +649,3 @@ class DatabaseManager:
         logger.info(f"Total transformed code documents: {len(transformed_code_documents)}")
         return transformed_doc_documents, transformed_code_documents
 
-    def prepare_retriever(self, repo_url_or_path: str, access_token: str = None):
-        """
-        Prepare the retriever for a repository.
-        This is a compatibility method for the isolated API.
-
-        Args:
-            repo_url_or_path (str): The URL or local path of the repository
-            access_token (str, optional): Access token for private repositories
-
-        Returns:
-            List[Document]: List of Document objects
-        """
-        return self.prepare_database(repo_url_or_path, access_token)

bioguider/rag/rag.py

@@ -50,22 +50,25 @@ class RAG(adal.Component):
     def initialize_db_manager(self):
         """Initialize the database manager with local storage"""
         self.db_manager = DatabaseManager()
-        self.transformed_doc_documents = []
-        self.transformed_code_documents = []
+        self.transformed_doc_documents: list | None = None
+        self.transformed_code_documents: list | None = None
+        self.access_token: str | None = None
 
-    def prepare_retriever(self, repo_url_or_path: str, access_token: str = None):
+    def initialize_repo(self, repo_url_or_path: str, access_token: str = None):
+        self.repo_url_or_path = repo_url_or_path
+        self.access_token = access_token
+        self.db_manager.reset_database_and_create_repo(repo_url_or_path, access_token)
+
+    def _prepare_retriever(self):
         """
         Prepare the retriever for a repository.
         Will load database from local storage if available.
-
-        Args:
-            repo_url_or_path: URL or local path to the repository
-            access_token: Optional access token for private repositories
         """
-        self.initialize_db_manager()
-        self.repo_url_or_path = repo_url_or_path
+        if self.transformed_code_documents is not None and self.transformed_doc_documents is not None:
+            # retrievers have been prepared
+            return
         self.transformed_doc_documents, self.transformed_code_documents \
-            = self.db_manager.prepare_database(repo_url_or_path, access_token)
+            = self.db_manager.prepare_database()
         logger.info(f"Loaded {len(self.transformed_doc_documents)} doc documents for retrieval")
         logger.info(f"Loaded {len(self.transformed_code_documents)} code documents for retrieval")
         self.doc_retriever = FAISSRetriever(
@@ -93,6 +96,7 @@ class RAG(adal.Component):
         Returns:
             retrieved_documents: List of documents retrieved based on the query
         """
+        self._prepare_retriever()
         retrieved_documents = self.doc_retriever(query)
         # Fill in the documents
         retrieved_documents[0].documents = [

{bioguider-0.2.8.dist-info → bioguider-0.2.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bioguider
-Version: 0.2.8
+Version: 0.2.10
 Summary: An AI-Powered package to help biomedical developers to generate clear documentation
 License: MIT
 Author: Cankun Wang

{bioguider-0.2.8.dist-info → bioguider-0.2.10.dist-info}/RECORD

@@ -1,7 +1,7 @@
 bioguider/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/agents/agent_task.py,sha256=SX4iLdGqQttT39qvr-RtXiSpQEzm7Z3ECVw8IGQzpDc,2828
-bioguider/agents/agent_tools.py,sha256=tl78zCdeWInv5DtwPEKKI4-7CLzfKlr646Sr3hjxo5g,6827
+bioguider/agents/agent_tools.py,sha256=YWF44vGjTzK0H9dxfdZyJ5K2H4z2j1bz-Q0bVw1UoE8,7014
 bioguider/agents/agent_utils.py,sha256=GASgM8pwGcbs3xQ8RaryBtWCim19rAcd3_c4EDranmU,12843
 bioguider/agents/collection_execute_step.py,sha256=Ev4BLjjmBdsc52M1zrq7QK8g7fsffDkSxu-jN2rvedw,5614
 bioguider/agents/collection_observe_step.py,sha256=iNeV6f16Emk1LMStSR4FXBPZ6Sc0eTjwxEfmoeegV-U,4554
@@ -9,17 +9,17 @@ bioguider/agents/collection_plan_step.py,sha256=mx-_5Y3pqKDPBaMMyFElKlpq1GWN7g03
 bioguider/agents/collection_task.py,sha256=blrsS71aR-Du0vtO4MpFI6q0aUJdMvlAAYvHb1pBUfY,7368
 bioguider/agents/collection_task_utils.py,sha256=WRzzpMV6r8aY0FlX_zroHbLDXyrmvS48OSiBr_fIq2Q,3677
 bioguider/agents/common_agent.py,sha256=eGs8m8bjO0dmW6lDIen7DQNdWdHD7j8Udf3XhL1k6vI,5242
-bioguider/agents/common_agent_2step.py,sha256=IJ5SxqsK26oj8W3U4wnGtbJxHRrHEznaGCYFBXKUHn4,7916
+bioguider/agents/common_agent_2step.py,sha256=Vton0RKtmMyEgIIFhnBk4CFU_hynX0LvwREcZ9kvMxQ,7918
 bioguider/agents/common_step.py,sha256=GdOCbmj1pwh4etg-futVFYVDQuoUG89DnIrw-B6QbzM,2594
 bioguider/agents/dockergeneration_execute_step.py,sha256=F92jDlkc6KjAvTkX7q1FsCYP8J15SCaNgmwh3YPqfDo,6500
 bioguider/agents/dockergeneration_observe_step.py,sha256=93PO_Y4YyUShVTKRt0nErcjb-xYTcwcZCj7TgniS9t4,6098
 bioguider/agents/dockergeneration_plan_step.py,sha256=SB8tQM9PkIKsD2o1DFD7bedcxz6r6hSy8n_EVK60Fz0,7235
 bioguider/agents/dockergeneration_task.py,sha256=ezsweVHJsFpOyOI6rYMt1DZ3PE19dcq4J3Lm-d0IA8M,6220
 bioguider/agents/dockergeneration_task_utils.py,sha256=v7emqrJlVW-A5ZdLmPSdiaMSKCR8uzy9UYzx_1cgzyo,9041
-bioguider/agents/evaluation_installation_task.py,sha256=Qrn5f-YpqAfaInTgErprDi54Lnufm8geZAhxmNhCqmE,6451
-bioguider/agents/evaluation_task.py,sha256=8tjRPGsRQ9qDxVgYYDo-GhhEiwW71zSS-iyLZUPRbBA,17178
+bioguider/agents/evaluation_installation_task.py,sha256=G8oFpyiT99bGyHGgqE6eCW6_i5le64i3Hd7hSQkrndE,6498
+bioguider/agents/evaluation_task.py,sha256=vZxjtj20BSGO5VP4-JdmiJRbg8pEzz664mjFTJioaZQ,17367
 bioguider/agents/identification_execute_step.py,sha256=w3IjL8f2WiHCyiLjVSoySnIAXpi1-hK1DLKCnXbAN2Y,5587
-bioguider/agents/identification_observe_step.py,sha256=OENwf9XyOSIHvJMp7eoyQOYGjjtPnPT2S29xf1rCATk,3667
+bioguider/agents/identification_observe_step.py,sha256=j4Fniv86jljkClTFc-p3pA39_zxhGJLPS9K7jNpxhJ0,3750
 bioguider/agents/identification_plan_step.py,sha256=p0BKziXdB4ph4D_T9FU5bH8CbHD5Gv0YuszMds_xh-Y,5224
 bioguider/agents/identification_task.py,sha256=vQxNEkX1Sw-XK391Z2_bi3kjr0tcIU1u6y7JBaEXUFU,8790
 bioguider/agents/identification_task_utils.py,sha256=5gevknha9hJiiQN5L7Yp9-pyhAlbR_j31aGRK5j0D_w,522
@@ -29,12 +29,12 @@ bioguider/agents/python_ast_repl_tool.py,sha256=o7-4P1h8jS8ikhGSA4CI_OWQ2a0Eg5tE
 bioguider/agents/rag_collection_task.py,sha256=r_jPAMjQcC7dIydKxX77UuMqjJ3MiVKswNZ-yNw7yx8,5199
 bioguider/conversation.py,sha256=DIvk_d7pz_guuORByK1eaaF09FAK-8shcNTrbSUHz9Y,1779
 bioguider/database/summarized_file_db.py,sha256=tDSi2iCvm2-lrx0rBJo0C11gYl9FswsDZTG2-Yhu5cE,4646
-bioguider/managers/evaluation_manager.py,sha256=93XOE2Q2a-mRa8DMF3IZC7mhE2CxxqOZZ5MLbWlPsjo,4904
+bioguider/managers/evaluation_manager.py,sha256=oQVcrJXR_ushU4IBT4yR0o6rXFHftfkJywrteGrkISY,4910
 bioguider/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/rag/config.py,sha256=5g4IqTzgyfZfax9Af9CTkXShgItPOt4_9TEMSekCPik,4602
-bioguider/rag/data_pipeline.py,sha256=OXnsqETVytHBMXHerg9gACtNhwpWSODYWvzxVDTP_So,27767
+bioguider/rag/data_pipeline.py,sha256=bkJ2IUCgPx_OL2uZtPd6cIBor2VFZEIfGd5kVlmiPjw,27292
 bioguider/rag/embedder.py,sha256=jofR8hOj3Aj2IyBQ9y6FeAc84tgq5agbIfCGyFxYpJ8,650
-bioguider/rag/rag.py,sha256=2G2b7JIDsjrR74lnkIFyEuMPF14kn6B-WhphZkUxd3c,4481
+bioguider/rag/rag.py,sha256=JFPwrJlKDSyd3U3Gce_NSxI5343eNUbqPG9Fs5Pfoq0,4696
 bioguider/settings.py,sha256=BD_iz9aYarxmWUl0XaKl4-D4oTXMhFzljsXLNn2phis,3143
 bioguider/utils/constants.py,sha256=_xMAhwE3py2RR0pIimnb2qfucXdnTj4ZNeKGACouh2w,932
 bioguider/utils/default.gitignore,sha256=XjPdyO2KV8z8iyuqluaNR_70tBQftMpyKL8HboVNyeI,1605
@@ -42,7 +42,7 @@ bioguider/utils/file_utils.py,sha256=9VfAHsz1UkFPtzAmvWZvPl1TMaKIYNjNlLgsfB8tNjg
 bioguider/utils/gitignore_checker.py,sha256=pOYUwsS9D5014LxcZb0cj3s2CAYaD2uF_pYJpaNKcho,6532
 bioguider/utils/pyphen_utils.py,sha256=cdZc3qphkvMDeL5NiZ8Xou13M_uVNP7ifJ-FwxO-0BE,2680
 bioguider/utils/utils.py,sha256=YP3HXgU_rvYDWkEcTzWGiYZw-mlfVrqGhUGSc0_4Pms,900
-bioguider-0.2.8.dist-info/LICENSE,sha256=qzkvZcKwwA5DuSuhXMOm2LcO6BdEr4V7jwFZVL2-jL4,1065
-bioguider-0.2.8.dist-info/METADATA,sha256=KgszAjfuux0wkXcAbcfchBJiBgwbuhm61YIMsBRJoWQ,1867
-bioguider-0.2.8.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-bioguider-0.2.8.dist-info/RECORD,,
+bioguider-0.2.10.dist-info/LICENSE,sha256=qzkvZcKwwA5DuSuhXMOm2LcO6BdEr4V7jwFZVL2-jL4,1065
+bioguider-0.2.10.dist-info/METADATA,sha256=OGjtW0XGNonKac0PuNjF4o_iNDuLk07t_4_0EVgfMtc,1868
+bioguider-0.2.10.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+bioguider-0.2.10.dist-info/RECORD,,